Guangxi Clinical Center for AIDS Prevention and Treatment, Chest Hospital of Guangxi Zhuang Autonomous Region, Liuzhou, Guangxi, China.
School of Information and Management, Guangxi Medical University, Nanning, Guangxi, China.
Front Public Health. 2023 Jul 28;11:1184831. doi: 10.3389/fpubh.2023.1184831. eCollection 2023.
Cytopenia is a frequent complication among HIV-infected patients who require hospitalization. It can have a negative impact on the treatment outcomes for these patients. However, by leveraging machine learning techniques and electronic medical records, a predictive model can be developed to evaluate the risk of cytopenia during hospitalization in HIV patients. Such a model is crucial for designing a more individualized and evidence-based treatment strategy for HIV patients.
The present study was conducted on HIV patients who were admitted to Guangxi Chest Hospital between June 2016 and October 2021. We extracted a total of 66 clinical features from the electronic medical records and employed them to train five machine learning prediction models (artificial neural network [ANN], adaptive boosting [AdaBoost], k-nearest neighbour [KNN] and support vector machine [SVM], decision tree [DT]). The models were tested using 20% of the data. The performance of the models was evaluated using indicators such as the area under the receiver operating characteristic curve (AUC). The best predictive models were interpreted using the shapley additive explanation (SHAP).
The ANN models have better predictive power. According to the SHAP interpretation of the ANN model, hypoproteinemia and cancer were the most important predictive features of cytopenia in HIV hospitalized patients. Meanwhile, the lower hemoglobin-to-RDW ratio (HGB/RDW), low-density lipoprotein cholesterol (LDL-C) levels, CD4 T cell counts, and creatinine clearance (Ccr) levels increase the risk of cytopenia in HIV hospitalized patients.
The present study constructed a risk prediction model for cytopenia in HIV patients during hospitalization with machine learning and electronic medical record information. The prediction model is important for the rational management of HIV hospitalized patients and the personalized treatment plan setting.
血细胞减少症是 HIV 感染患者住院的常见并发症。它会对这些患者的治疗结果产生负面影响。然而，通过利用机器学习技术和电子病历，可以开发出一种预测模型，以评估 HIV 患者住院期间发生血细胞减少症的风险。对于为 HIV 患者设计更个性化和基于证据的治疗策略，这种模型至关重要。
本研究纳入了 2016 年 6 月至 2021 年 10 月期间在广西壮族自治区胸科医院住院的 HIV 患者。我们从电子病历中提取了 66 个临床特征，并将其用于训练 5 种机器学习预测模型（人工神经网络[ANN]、自适应增强[AdaBoost]、k-最近邻[KNN]和支持向量机[SVM]、决策树[DT]）。使用 20%的数据测试模型。使用受试者工作特征曲线下面积（AUC）等指标评估模型的性能。使用 shapley 加性解释（SHAP）对最佳预测模型进行解释。
ANN 模型具有更好的预测能力。根据 ANN 模型的 SHAP 解释，低蛋白血症和癌症是 HIV 住院患者血细胞减少症的最重要预测特征。同时，血红蛋白与红细胞分布宽度的比值（HGB/RDW）、低密度脂蛋白胆固醇（LDL-C）水平、CD4 T 细胞计数和肌酐清除率（Ccr）降低会增加 HIV 住院患者发生血细胞减少症的风险。
本研究使用机器学习和电子病历信息构建了 HIV 患者住院期间血细胞减少症的风险预测模型。该预测模型对于 HIV 住院患者的合理管理和个性化治疗方案的制定非常重要。
